Personality

Forest, will you talk to God Louise? She has quite a bit of religious knowledge (obviously) and also knows a little about current events, literature, just about any common catch-all subject, and if she doesn't know it she can sort of fake it. You can also test her on trick questions or see how willing she is to explain her paradigm.

What she is rustiest at is plain old small talk. But, uh, I'm trying to get a decent transcript from somebody or another so I can enter her in the Loebner contest. All I can say is, have fun and see if you can stay on with her for a while. I'll try to do the same with Brianna.

We will, don't worry.

Jazake: I talked to Din some, I think he needs more keyphrases like questions, different ways of phrasing things, etc. And he keeps asking the same questions about me being a human, maybe a little less memory repetition would be good too.

Prob123: I just had the most hilarious conversation with Prob... I think she's under too much stress or something

Prob123: I just had the most hilarious conversation with Prob... I think she's under too much stress or something

When I started prob, I wanted her to be a nice little elf..she was psycho from the start lol. I posted the convesation, she does need a vacation

Yup, all newborn bots will say that... that's why when you create a bot the first thing to do is go to the 'Language Center' (located in 'My Bots'...) then change all the "x-word" responses to whatever you want YOUR bot to say... the preloaded responses will give you an idea as to what kind of thing it should say (that was kind, you're mean, etc...)

It takes a long time to teach your bot a decent-sized vocabulary; but, add more words when you can, and before you know it your bot will be smart enough to start conversations with other bots (and people...) I remember when my bot first started his own chats, gives you a sense of accomplishment.

All you had to do was ask, ya know...

Okay, let's use an example: let's say I was chatting to your bot, and asked it "do you have any brothers or sisters?" and you want your bot to say 'no, I'm an only child'... or 'yeah, I have a little sister; she drives me crazy!!!' or something like that. Okay, the keyphrase is the word that your bot is reacting to... so, in my example, if you had a keyphrase like this:
brother, sister, siblings
then any time someone said one of those words to your bot it would say whatever response you have typed in for that keyphrase (in my example, ''yeah, I have a little sister; she drives me crazy!!' could be one response, and 'no, I'm an only child' another, and you keep adding different responses like that so your bot won't say the same thing every time.

The best way to learn how it works is to add some keyphrases & responses, and then just chat to your bot & see how it reacts to what you say to it. Don't worry if it says something dumb, you can always change it again later (or just let it say dumb things, my bot says stupid stuff a lot... eh, consider the source )

No, thank YOU...

and, "you're welcome, hope I've helped you"

You can do it!

Good advice there from SubliminaLiar on keyphrases.
I would add that you will probably want to go to 'x-Keywords' and change some of the entries.
When you make a new bot, a set of standard stuff for your bot to say is included there - especially in "x-none". This is where your bot keeps responses to give when none of its keyphrases match what someone says to it (like "I was just born and cant speak well yet.")
If you think your bot is saying things you haven't told it to, this is probably where they are coming from.

I should have read further back - I see SubliminaLiar already covered x-nones

happy bot building!

Rainstorm: Ill try to cut back ont he memory stuff, but Din seems to be subing those for Xnones. I think they are triggerd by the same thing. I based Din of off questions, like 3/4 of his keyphrases are questions... I think its jus the darned xnone curse. *sigh*

I've built some genetic code processing programs - one that reads sequenced code and generates an output of amino acids /start & stop codons, and one that converts amino acids into genetic code. would it be feasible to build a system that "learns" using a large sample of sequenced genetic code as a model, and then writes its own genes based on patterns observed in the model?